Training in progress, step 500
Browse files- .gitignore +1 -0
- added_tokens.json +3 -0
- config.json +154 -0
- merges.txt +0 -0
- preprocessor_config.json +14 -0
- pytorch_model.bin +3 -0
- runs/Jul26_13-13-15_a54229703d85/events.out.tfevents.1690377593.a54229703d85.8171.0 +3 -0
- special_tokens_map.json +115 -0
- tokenizer_config.json +151 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|ckb|>": 50257
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openai/whisper-tiny",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"apply_spec_augment": false,
|
6 |
+
"architectures": [
|
7 |
+
"WhisperForConditionalGeneration"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"begin_suppress_tokens": [
|
11 |
+
220,
|
12 |
+
50257
|
13 |
+
],
|
14 |
+
"bos_token_id": 50257,
|
15 |
+
"classifier_proj_size": 256,
|
16 |
+
"d_model": 384,
|
17 |
+
"decoder_attention_heads": 6,
|
18 |
+
"decoder_ffn_dim": 1536,
|
19 |
+
"decoder_layerdrop": 0.0,
|
20 |
+
"decoder_layers": 4,
|
21 |
+
"decoder_start_token_id": 50258,
|
22 |
+
"dropout": 0.0,
|
23 |
+
"encoder_attention_heads": 6,
|
24 |
+
"encoder_ffn_dim": 1536,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 4,
|
27 |
+
"eos_token_id": 50257,
|
28 |
+
"forced_decoder_ids": [
|
29 |
+
[
|
30 |
+
1,
|
31 |
+
50259
|
32 |
+
],
|
33 |
+
[
|
34 |
+
2,
|
35 |
+
50359
|
36 |
+
],
|
37 |
+
[
|
38 |
+
3,
|
39 |
+
50363
|
40 |
+
]
|
41 |
+
],
|
42 |
+
"init_std": 0.02,
|
43 |
+
"is_encoder_decoder": true,
|
44 |
+
"mask_feature_length": 10,
|
45 |
+
"mask_feature_min_masks": 0,
|
46 |
+
"mask_feature_prob": 0.0,
|
47 |
+
"mask_time_length": 10,
|
48 |
+
"mask_time_min_masks": 2,
|
49 |
+
"mask_time_prob": 0.05,
|
50 |
+
"max_length": 448,
|
51 |
+
"max_source_positions": 1500,
|
52 |
+
"max_target_positions": 448,
|
53 |
+
"median_filter_width": 7,
|
54 |
+
"model_type": "whisper",
|
55 |
+
"num_hidden_layers": 4,
|
56 |
+
"num_mel_bins": 80,
|
57 |
+
"pad_token_id": 50257,
|
58 |
+
"scale_embedding": false,
|
59 |
+
"suppress_tokens": [
|
60 |
+
1,
|
61 |
+
2,
|
62 |
+
7,
|
63 |
+
8,
|
64 |
+
9,
|
65 |
+
10,
|
66 |
+
14,
|
67 |
+
25,
|
68 |
+
26,
|
69 |
+
27,
|
70 |
+
28,
|
71 |
+
29,
|
72 |
+
31,
|
73 |
+
58,
|
74 |
+
59,
|
75 |
+
60,
|
76 |
+
61,
|
77 |
+
62,
|
78 |
+
63,
|
79 |
+
90,
|
80 |
+
91,
|
81 |
+
92,
|
82 |
+
93,
|
83 |
+
359,
|
84 |
+
503,
|
85 |
+
522,
|
86 |
+
542,
|
87 |
+
873,
|
88 |
+
893,
|
89 |
+
902,
|
90 |
+
918,
|
91 |
+
922,
|
92 |
+
931,
|
93 |
+
1350,
|
94 |
+
1853,
|
95 |
+
1982,
|
96 |
+
2460,
|
97 |
+
2627,
|
98 |
+
3246,
|
99 |
+
3253,
|
100 |
+
3268,
|
101 |
+
3536,
|
102 |
+
3846,
|
103 |
+
3961,
|
104 |
+
4183,
|
105 |
+
4667,
|
106 |
+
6585,
|
107 |
+
6647,
|
108 |
+
7273,
|
109 |
+
9061,
|
110 |
+
9383,
|
111 |
+
10428,
|
112 |
+
10929,
|
113 |
+
11938,
|
114 |
+
12033,
|
115 |
+
12331,
|
116 |
+
12562,
|
117 |
+
13793,
|
118 |
+
14157,
|
119 |
+
14635,
|
120 |
+
15265,
|
121 |
+
15618,
|
122 |
+
16553,
|
123 |
+
16604,
|
124 |
+
18362,
|
125 |
+
18956,
|
126 |
+
20075,
|
127 |
+
21675,
|
128 |
+
22520,
|
129 |
+
26130,
|
130 |
+
26161,
|
131 |
+
26435,
|
132 |
+
28279,
|
133 |
+
29464,
|
134 |
+
31650,
|
135 |
+
32302,
|
136 |
+
32470,
|
137 |
+
36865,
|
138 |
+
42863,
|
139 |
+
47425,
|
140 |
+
49870,
|
141 |
+
50254,
|
142 |
+
50258,
|
143 |
+
50358,
|
144 |
+
50359,
|
145 |
+
50360,
|
146 |
+
50361,
|
147 |
+
50362
|
148 |
+
],
|
149 |
+
"torch_dtype": "float32",
|
150 |
+
"transformers_version": "4.31.0",
|
151 |
+
"use_cache": false,
|
152 |
+
"use_weighted_layer_sum": false,
|
153 |
+
"vocab_size": 51865
|
154 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
preprocessor_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chunk_length": 30,
|
3 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
4 |
+
"feature_size": 80,
|
5 |
+
"hop_length": 160,
|
6 |
+
"n_fft": 400,
|
7 |
+
"n_samples": 480000,
|
8 |
+
"nb_max_frames": 3000,
|
9 |
+
"padding_side": "right",
|
10 |
+
"padding_value": 0.0,
|
11 |
+
"processor_class": "WhisperProcessor",
|
12 |
+
"return_attention_mask": false,
|
13 |
+
"sampling_rate": 16000
|
14 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63391af6ed1d6ad5056065fa8390de10e401a06c83657e0aabfc47eba9174290
|
3 |
+
size 151099049
|
runs/Jul26_13-13-15_a54229703d85/events.out.tfevents.1690377593.a54229703d85.8171.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f859b369c919c23cba3af016480ceba832bb97c281d9ed2de5ce71e99d351d1
|
3 |
+
size 9340
|
special_tokens_map.json
ADDED
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|startoftranscript|>",
|
4 |
+
"<|ckb|>",
|
5 |
+
"<|en|>",
|
6 |
+
"<|zh|>",
|
7 |
+
"<|de|>",
|
8 |
+
"<|es|>",
|
9 |
+
"<|ru|>",
|
10 |
+
"<|ko|>",
|
11 |
+
"<|fr|>",
|
12 |
+
"<|ja|>",
|
13 |
+
"<|pt|>",
|
14 |
+
"<|tr|>",
|
15 |
+
"<|pl|>",
|
16 |
+
"<|ca|>",
|
17 |
+
"<|nl|>",
|
18 |
+
"<|ar|>",
|
19 |
+
"<|sv|>",
|
20 |
+
"<|it|>",
|
21 |
+
"<|id|>",
|
22 |
+
"<|hi|>",
|
23 |
+
"<|fi|>",
|
24 |
+
"<|vi|>",
|
25 |
+
"<|iw|>",
|
26 |
+
"<|uk|>",
|
27 |
+
"<|el|>",
|
28 |
+
"<|ms|>",
|
29 |
+
"<|cs|>",
|
30 |
+
"<|ro|>",
|
31 |
+
"<|da|>",
|
32 |
+
"<|hu|>",
|
33 |
+
"<|ta|>",
|
34 |
+
"<|no|>",
|
35 |
+
"<|th|>",
|
36 |
+
"<|ur|>",
|
37 |
+
"<|hr|>",
|
38 |
+
"<|bg|>",
|
39 |
+
"<|lt|>",
|
40 |
+
"<|la|>",
|
41 |
+
"<|mi|>",
|
42 |
+
"<|ml|>",
|
43 |
+
"<|cy|>",
|
44 |
+
"<|sk|>",
|
45 |
+
"<|te|>",
|
46 |
+
"<|fa|>",
|
47 |
+
"<|lv|>",
|
48 |
+
"<|bn|>",
|
49 |
+
"<|sr|>",
|
50 |
+
"<|az|>",
|
51 |
+
"<|sl|>",
|
52 |
+
"<|kn|>",
|
53 |
+
"<|et|>",
|
54 |
+
"<|mk|>",
|
55 |
+
"<|br|>",
|
56 |
+
"<|eu|>",
|
57 |
+
"<|is|>",
|
58 |
+
"<|hy|>",
|
59 |
+
"<|ne|>",
|
60 |
+
"<|mn|>",
|
61 |
+
"<|bs|>",
|
62 |
+
"<|kk|>",
|
63 |
+
"<|sq|>",
|
64 |
+
"<|sw|>",
|
65 |
+
"<|gl|>",
|
66 |
+
"<|mr|>",
|
67 |
+
"<|pa|>",
|
68 |
+
"<|si|>",
|
69 |
+
"<|km|>",
|
70 |
+
"<|sn|>",
|
71 |
+
"<|yo|>",
|
72 |
+
"<|so|>",
|
73 |
+
"<|af|>",
|
74 |
+
"<|oc|>",
|
75 |
+
"<|ka|>",
|
76 |
+
"<|be|>",
|
77 |
+
"<|tg|>",
|
78 |
+
"<|sd|>",
|
79 |
+
"<|gu|>",
|
80 |
+
"<|am|>",
|
81 |
+
"<|yi|>",
|
82 |
+
"<|lo|>",
|
83 |
+
"<|uz|>",
|
84 |
+
"<|fo|>",
|
85 |
+
"<|ht|>",
|
86 |
+
"<|ps|>",
|
87 |
+
"<|tk|>",
|
88 |
+
"<|nn|>",
|
89 |
+
"<|mt|>",
|
90 |
+
"<|sa|>",
|
91 |
+
"<|lb|>",
|
92 |
+
"<|my|>",
|
93 |
+
"<|bo|>",
|
94 |
+
"<|tl|>",
|
95 |
+
"<|mg|>",
|
96 |
+
"<|as|>",
|
97 |
+
"<|tt|>",
|
98 |
+
"<|haw|>",
|
99 |
+
"<|ln|>",
|
100 |
+
"<|ha|>",
|
101 |
+
"<|ba|>",
|
102 |
+
"<|jw|>",
|
103 |
+
"<|su|>",
|
104 |
+
"<|translate|>",
|
105 |
+
"<|transcribe|>",
|
106 |
+
"<|startoflm|>",
|
107 |
+
"<|startofprev|>",
|
108 |
+
"<|nocaptions|>",
|
109 |
+
"<|notimestamps|>"
|
110 |
+
],
|
111 |
+
"bos_token": "<|endoftext|>",
|
112 |
+
"eos_token": "<|endoftext|>",
|
113 |
+
"pad_token": "<|endoftext|>",
|
114 |
+
"unk_token": "<|endoftext|>"
|
115 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,151 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"additional_special_tokens": [
|
5 |
+
"<|startoftranscript|>",
|
6 |
+
"<|ckb|>",
|
7 |
+
"<|en|>",
|
8 |
+
"<|zh|>",
|
9 |
+
"<|de|>",
|
10 |
+
"<|es|>",
|
11 |
+
"<|ru|>",
|
12 |
+
"<|ko|>",
|
13 |
+
"<|fr|>",
|
14 |
+
"<|ja|>",
|
15 |
+
"<|pt|>",
|
16 |
+
"<|tr|>",
|
17 |
+
"<|pl|>",
|
18 |
+
"<|ca|>",
|
19 |
+
"<|nl|>",
|
20 |
+
"<|ar|>",
|
21 |
+
"<|sv|>",
|
22 |
+
"<|it|>",
|
23 |
+
"<|id|>",
|
24 |
+
"<|hi|>",
|
25 |
+
"<|fi|>",
|
26 |
+
"<|vi|>",
|
27 |
+
"<|iw|>",
|
28 |
+
"<|uk|>",
|
29 |
+
"<|el|>",
|
30 |
+
"<|ms|>",
|
31 |
+
"<|cs|>",
|
32 |
+
"<|ro|>",
|
33 |
+
"<|da|>",
|
34 |
+
"<|hu|>",
|
35 |
+
"<|ta|>",
|
36 |
+
"<|no|>",
|
37 |
+
"<|th|>",
|
38 |
+
"<|ur|>",
|
39 |
+
"<|hr|>",
|
40 |
+
"<|bg|>",
|
41 |
+
"<|lt|>",
|
42 |
+
"<|la|>",
|
43 |
+
"<|mi|>",
|
44 |
+
"<|ml|>",
|
45 |
+
"<|cy|>",
|
46 |
+
"<|sk|>",
|
47 |
+
"<|te|>",
|
48 |
+
"<|fa|>",
|
49 |
+
"<|lv|>",
|
50 |
+
"<|bn|>",
|
51 |
+
"<|sr|>",
|
52 |
+
"<|az|>",
|
53 |
+
"<|sl|>",
|
54 |
+
"<|kn|>",
|
55 |
+
"<|et|>",
|
56 |
+
"<|mk|>",
|
57 |
+
"<|br|>",
|
58 |
+
"<|eu|>",
|
59 |
+
"<|is|>",
|
60 |
+
"<|hy|>",
|
61 |
+
"<|ne|>",
|
62 |
+
"<|mn|>",
|
63 |
+
"<|bs|>",
|
64 |
+
"<|kk|>",
|
65 |
+
"<|sq|>",
|
66 |
+
"<|sw|>",
|
67 |
+
"<|gl|>",
|
68 |
+
"<|mr|>",
|
69 |
+
"<|pa|>",
|
70 |
+
"<|si|>",
|
71 |
+
"<|km|>",
|
72 |
+
"<|sn|>",
|
73 |
+
"<|yo|>",
|
74 |
+
"<|so|>",
|
75 |
+
"<|af|>",
|
76 |
+
"<|oc|>",
|
77 |
+
"<|ka|>",
|
78 |
+
"<|be|>",
|
79 |
+
"<|tg|>",
|
80 |
+
"<|sd|>",
|
81 |
+
"<|gu|>",
|
82 |
+
"<|am|>",
|
83 |
+
"<|yi|>",
|
84 |
+
"<|lo|>",
|
85 |
+
"<|uz|>",
|
86 |
+
"<|fo|>",
|
87 |
+
"<|ht|>",
|
88 |
+
"<|ps|>",
|
89 |
+
"<|tk|>",
|
90 |
+
"<|nn|>",
|
91 |
+
"<|mt|>",
|
92 |
+
"<|sa|>",
|
93 |
+
"<|lb|>",
|
94 |
+
"<|my|>",
|
95 |
+
"<|bo|>",
|
96 |
+
"<|tl|>",
|
97 |
+
"<|mg|>",
|
98 |
+
"<|as|>",
|
99 |
+
"<|tt|>",
|
100 |
+
"<|haw|>",
|
101 |
+
"<|ln|>",
|
102 |
+
"<|ha|>",
|
103 |
+
"<|ba|>",
|
104 |
+
"<|jw|>",
|
105 |
+
"<|su|>",
|
106 |
+
"<|translate|>",
|
107 |
+
"<|transcribe|>",
|
108 |
+
"<|startoflm|>",
|
109 |
+
"<|startofprev|>",
|
110 |
+
"<|nocaptions|>",
|
111 |
+
"<|notimestamps|>"
|
112 |
+
],
|
113 |
+
"bos_token": {
|
114 |
+
"__type": "AddedToken",
|
115 |
+
"content": "<|endoftext|>",
|
116 |
+
"lstrip": false,
|
117 |
+
"normalized": true,
|
118 |
+
"rstrip": false,
|
119 |
+
"single_word": false
|
120 |
+
},
|
121 |
+
"clean_up_tokenization_spaces": true,
|
122 |
+
"eos_token": {
|
123 |
+
"__type": "AddedToken",
|
124 |
+
"content": "<|endoftext|>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": true,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false
|
129 |
+
},
|
130 |
+
"errors": "replace",
|
131 |
+
"model_max_length": 1024,
|
132 |
+
"pad_token": {
|
133 |
+
"__type": "AddedToken",
|
134 |
+
"content": "<|endoftext|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": true,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false
|
139 |
+
},
|
140 |
+
"processor_class": "WhisperProcessor",
|
141 |
+
"return_attention_mask": false,
|
142 |
+
"tokenizer_class": "WhisperTokenizer",
|
143 |
+
"unk_token": {
|
144 |
+
"__type": "AddedToken",
|
145 |
+
"content": "<|endoftext|>",
|
146 |
+
"lstrip": false,
|
147 |
+
"normalized": true,
|
148 |
+
"rstrip": false,
|
149 |
+
"single_word": false
|
150 |
+
}
|
151 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2210364eed625b246c644ab46f8f4c2e85408ef16605105e1d3c1f20b080b27b
|
3 |
+
size 4091
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|